Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1268 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.6369. Min Act: -0.0000

Data Index: 1631952 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.8411. Min Act: -0.0000

Data Index: 974542 (The Pile)

Max Activating Token Index: 412

Text #2

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.5059. Min Act: -0.0000

Data Index: 1690645 (The Pile)

Max Activating Token Index: 745

Text #3

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.2026. Min Act: -0.0000

Data Index: 777129 (The Pile)

Max Activating Token Index: 775

Text #4

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.4717. Min Act: -0.0000

Data Index: 1089310 (The Pile)

Max Activating Token Index: 365

Text #5

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.1378. Min Act: -0.0000

Data Index: 1394022 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.1964. Min Act: -0.0000

Data Index: 809330 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.2926. Min Act: -0.0000

Data Index: 804549 (The Pile)

Max Activating Token Index: 328

Text #8

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.1227. Min Act: -0.0000

Data Index: 1620625 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 3.8411. Min Range: -3.8411

Max Act: 2.7992. Min Act: -0.0000

Data Index: 1663203 (The Pile)

Max Activating Token Index: 679

Text #10

Max Range: 3.8411. Min Range: -3.8411

Max Act: 2.9392. Min Act: -0.0000

Data Index: 997699 (The Pile)

Max Activating Token Index: 775

Text #11

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.0426. Min Act: -0.0000

Data Index: 1603722 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.0593. Min Act: -0.0000

Data Index: 1765028 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 3.8411. Min Range: -3.8411

Max Act: 2.9474. Min Act: -0.0000

Data Index: 1696824 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.1163. Min Act: -0.0000

Data Index: 623530 (The Pile)

Max Activating Token Index: 629

Text #15

Max Range: 3.8411. Min Range: -3.8411

Max Act: 3.0018. Min Act: -0.0000

Data Index: 703041 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 3.8411. Min Range: -3.8411

Max Act: 2.6562. Min Act: -0.0000

Data Index: 1796559 (The Pile)

Max Activating Token Index: 545

Text #17

Max Range: 3.8411. Min Range: -3.8411

Max Act: 2.8141. Min Act: -0.0000

Data Index: 447576 (The Pile)

Max Activating Token Index: 79

Text #18

Max Range: 3.8411. Min Range: -3.8411

Max Act: 2.5489. Min Act: -0.0000

Data Index: 97889 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 3.8411. Min Range: -3.8411

Max Act: 2.7460. Min Act: -0.0000

Data Index: 1291293 (The Pile)

Max Activating Token Index: 57